Monte-Carlo Convolutions on Foveated Images

George Killick, Gerardo Aragon-Camarasa, J. Paul Siebert

2022

Abstract

Foveated vision captures a visual scene at space-variant resolution. This makes the application of parameterized convolutions to foveated images difficult as they do not have a dense-grid representation in cartesian space. Log-polar space is frequently used to create a dense grid representation of foveated images, however this image representation may not be appropriate for all applications. In this paper we rephrase the convolution operation as the Monte-Carlo estimation of the filter response of the foveated image and a continuous filter kernel, an idea that has seen frequent use for deep learning on point clouds. We subsume our convolution operation into a simple CNN architecture that processes foveated images in cartesian space. We evaluate our system in the context of image classification and show that our approach significantly outperforms an equivalent CNN processing a foveated image in log-polar space.

Download


Paper Citation


in Harvard Style

Killick G., Aragon-Camarasa G. and Siebert J. (2022). Monte-Carlo Convolutions on Foveated Images. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP; ISBN 978-989-758-555-5, SciTePress, pages 444-451. DOI: 10.5220/0010832400003124


in Bibtex Style

@conference{visapp22,
author={George Killick and Gerardo Aragon-Camarasa and J. Paul Siebert},
title={Monte-Carlo Convolutions on Foveated Images},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP},
year={2022},
pages={444-451},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010832400003124},
isbn={978-989-758-555-5},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP
TI - Monte-Carlo Convolutions on Foveated Images
SN - 978-989-758-555-5
AU - Killick G.
AU - Aragon-Camarasa G.
AU - Siebert J.
PY - 2022
SP - 444
EP - 451
DO - 10.5220/0010832400003124
PB - SciTePress